# Ordered or Orderless: A Revisit for Video based Person Re-Identification

arXiv: https://arxiv.org/abs/1912.11236 · HTML: https://mlsanity.com/paper/1912.11236/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Adversarial Attack and Defense in Deep Ranking](https://mlsanity.com/paper/2106.03614/) (2021)
- [Semi-Supervised Domain Generalizable Person Re-Identification](https://mlsanity.com/paper/2108.05045/) (2021)
- [Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification](https://mlsanity.com/paper/2301.00531/) (2023)
- [Unsupervised Person Re-Identification with Wireless Positioning under Weak Scene Labeling](https://mlsanity.com/paper/2110.15610/) (2021)
- [Deep Learning for Video-based Person Re-Identification: A Survey](https://mlsanity.com/paper/2303.11332/) (2023)
- [Deep Negative Correlation Classification](https://mlsanity.com/paper/2212.07070/) (2022)
- [Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering](https://mlsanity.com/paper/2108.01431/) (2021)

## Abstract (arXiv)

Is recurrent network really necessary for learning a good visual representation for video based person re-identification (VPRe-id)? In this paper, we first show that the common practice of employing recurrent neural networks (RNNs) to aggregate temporal spatial features may not be optimal. Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective to learn temporal dependencies than what we expected and implicitly yields an orderless representation. Based on this observation, we then present a simple yet surprisingly powerful approach for VPRe-id, where we treat VPRe-id as an efficient orderless ensemble of image based person re-identification problem. More specifically, we divide videos into individual images and re-identify person with ensemble of image based rankers. Under the i.i.d. assumption, we provide an error bound that sheds light upon how could we improve VPRe-id. Our work also presents a promising way to bridge the gap between video and image based person re-identification. Comprehensive experimental evaluations demonstrate that the proposed solution achieves state-of-the-art performances on multiple widely used datasets (iLIDS-VID, PRID 2011, and MARS).